sedrickkeh commited on
Commit
3582c8d
·
verified ·
1 Parent(s): f49f6bc

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: top_12_ranking_stackexchange
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # top_12_ranking_stackexchange
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.7993
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: top_12_ranking_stackexchange
 
16
 
17
  # top_12_ranking_stackexchange
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/top_12_ranking_stackexchange dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.7993
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.994661421747682,
3
+ "eval_loss": 0.7992855906486511,
4
+ "eval_runtime": 479.0724,
5
+ "eval_samples_per_second": 25.023,
6
+ "eval_steps_per_second": 0.392,
7
+ "total_flos": 2230940231270400.0,
8
+ "train_loss": 0.7792791328630648,
9
+ "train_runtime": 78935.918,
10
+ "train_samples_per_second": 8.656,
11
+ "train_steps_per_second": 0.017
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.994661421747682,
3
+ "eval_loss": 0.7992855906486511,
4
+ "eval_runtime": 479.0724,
5
+ "eval_samples_per_second": 25.023,
6
+ "eval_steps_per_second": 0.392
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.994661421747682,
3
+ "total_flos": 2230940231270400.0,
4
+ "train_loss": 0.7792791328630648,
5
+ "train_runtime": 78935.918,
6
+ "train_samples_per_second": 8.656,
7
+ "train_steps_per_second": 0.017
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,997 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.994661421747682,
5
+ "eval_steps": 500,
6
+ "global_step": 1332,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.022478224220286596,
13
+ "grad_norm": 33.33372823372105,
14
+ "learning_rate": 5e-06,
15
+ "loss": 1.0579,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.04495644844057319,
20
+ "grad_norm": 1.0746818341634412,
21
+ "learning_rate": 5e-06,
22
+ "loss": 0.9596,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.0674346726608598,
27
+ "grad_norm": 0.7321847735876122,
28
+ "learning_rate": 5e-06,
29
+ "loss": 0.911,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08991289688114638,
34
+ "grad_norm": 0.7413785484127575,
35
+ "learning_rate": 5e-06,
36
+ "loss": 0.8985,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.11239112110143298,
41
+ "grad_norm": 0.6455791890910528,
42
+ "learning_rate": 5e-06,
43
+ "loss": 0.8815,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1348693453217196,
48
+ "grad_norm": 0.6017747724297141,
49
+ "learning_rate": 5e-06,
50
+ "loss": 0.8721,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.15734756954200618,
55
+ "grad_norm": 0.6032337358958032,
56
+ "learning_rate": 5e-06,
57
+ "loss": 0.8712,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.17982579376229277,
62
+ "grad_norm": 0.7856142351722715,
63
+ "learning_rate": 5e-06,
64
+ "loss": 0.8628,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.20230401798257938,
69
+ "grad_norm": 0.53309068117808,
70
+ "learning_rate": 5e-06,
71
+ "loss": 0.8619,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.22478224220286597,
76
+ "grad_norm": 0.7302586105980624,
77
+ "learning_rate": 5e-06,
78
+ "loss": 0.8536,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.24726046642315258,
83
+ "grad_norm": 0.5590012456129412,
84
+ "learning_rate": 5e-06,
85
+ "loss": 0.8494,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2697386906434392,
90
+ "grad_norm": 0.8024116489610613,
91
+ "learning_rate": 5e-06,
92
+ "loss": 0.8481,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.29221691486372575,
97
+ "grad_norm": 0.879956013299429,
98
+ "learning_rate": 5e-06,
99
+ "loss": 0.8416,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.31469513908401237,
104
+ "grad_norm": 0.7724424487225131,
105
+ "learning_rate": 5e-06,
106
+ "loss": 0.8459,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.337173363304299,
111
+ "grad_norm": 0.7280953369087129,
112
+ "learning_rate": 5e-06,
113
+ "loss": 0.8407,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.35965158752458554,
118
+ "grad_norm": 0.549976756286124,
119
+ "learning_rate": 5e-06,
120
+ "loss": 0.8383,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.38212981174487215,
125
+ "grad_norm": 0.6289114641518077,
126
+ "learning_rate": 5e-06,
127
+ "loss": 0.835,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.40460803596515876,
132
+ "grad_norm": 0.6648128128576364,
133
+ "learning_rate": 5e-06,
134
+ "loss": 0.834,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.4270862601854454,
139
+ "grad_norm": 0.5103947816514711,
140
+ "learning_rate": 5e-06,
141
+ "loss": 0.8365,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.44956448440573193,
146
+ "grad_norm": 0.6232935960390383,
147
+ "learning_rate": 5e-06,
148
+ "loss": 0.8326,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.47204270862601855,
153
+ "grad_norm": 0.6038963808726584,
154
+ "learning_rate": 5e-06,
155
+ "loss": 0.8335,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.49452093284630516,
160
+ "grad_norm": 0.5922907804331954,
161
+ "learning_rate": 5e-06,
162
+ "loss": 0.8295,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.5169991570665917,
167
+ "grad_norm": 0.585830487528667,
168
+ "learning_rate": 5e-06,
169
+ "loss": 0.8252,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5394773812868784,
174
+ "grad_norm": 0.5455286191351291,
175
+ "learning_rate": 5e-06,
176
+ "loss": 0.8295,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.561955605507165,
181
+ "grad_norm": 0.5826278411995965,
182
+ "learning_rate": 5e-06,
183
+ "loss": 0.8309,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5844338297274515,
188
+ "grad_norm": 0.628487407925322,
189
+ "learning_rate": 5e-06,
190
+ "loss": 0.8291,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.6069120539477382,
195
+ "grad_norm": 0.5179593922905324,
196
+ "learning_rate": 5e-06,
197
+ "loss": 0.8224,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.6293902781680247,
202
+ "grad_norm": 0.6849863947657101,
203
+ "learning_rate": 5e-06,
204
+ "loss": 0.8286,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6518685023883113,
209
+ "grad_norm": 0.5306421600279095,
210
+ "learning_rate": 5e-06,
211
+ "loss": 0.8239,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.674346726608598,
216
+ "grad_norm": 0.5652336198819432,
217
+ "learning_rate": 5e-06,
218
+ "loss": 0.823,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6968249508288845,
223
+ "grad_norm": 0.5081331704644918,
224
+ "learning_rate": 5e-06,
225
+ "loss": 0.8234,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.7193031750491711,
230
+ "grad_norm": 0.5996298789398387,
231
+ "learning_rate": 5e-06,
232
+ "loss": 0.8254,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.7417813992694577,
237
+ "grad_norm": 0.5164629633736417,
238
+ "learning_rate": 5e-06,
239
+ "loss": 0.8169,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7642596234897443,
244
+ "grad_norm": 0.4728695844824827,
245
+ "learning_rate": 5e-06,
246
+ "loss": 0.8189,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7867378477100309,
251
+ "grad_norm": 0.5186229875938196,
252
+ "learning_rate": 5e-06,
253
+ "loss": 0.819,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.8092160719303175,
258
+ "grad_norm": 0.6132017941059994,
259
+ "learning_rate": 5e-06,
260
+ "loss": 0.8165,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.8316942961506041,
265
+ "grad_norm": 0.53282736043642,
266
+ "learning_rate": 5e-06,
267
+ "loss": 0.8196,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.8541725203708908,
272
+ "grad_norm": 0.5547116807812702,
273
+ "learning_rate": 5e-06,
274
+ "loss": 0.8219,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8766507445911773,
279
+ "grad_norm": 0.5185569454044568,
280
+ "learning_rate": 5e-06,
281
+ "loss": 0.8155,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.8991289688114639,
286
+ "grad_norm": 0.5854723337738515,
287
+ "learning_rate": 5e-06,
288
+ "loss": 0.8153,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.9216071930317505,
293
+ "grad_norm": 0.535827573700132,
294
+ "learning_rate": 5e-06,
295
+ "loss": 0.8116,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.9440854172520371,
300
+ "grad_norm": 0.6607158975384394,
301
+ "learning_rate": 5e-06,
302
+ "loss": 0.8109,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.9665636414723237,
307
+ "grad_norm": 0.5944011061376792,
308
+ "learning_rate": 5e-06,
309
+ "loss": 0.8117,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9890418656926103,
314
+ "grad_norm": 0.5508674094850188,
315
+ "learning_rate": 5e-06,
316
+ "loss": 0.8066,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9980331553807249,
321
+ "eval_loss": 0.8152613639831543,
322
+ "eval_runtime": 475.9259,
323
+ "eval_samples_per_second": 25.189,
324
+ "eval_steps_per_second": 0.395,
325
+ "step": 444
326
+ },
327
+ {
328
+ "epoch": 1.0118010677156504,
329
+ "grad_norm": 0.7278302813509685,
330
+ "learning_rate": 5e-06,
331
+ "loss": 0.8129,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0342792919359372,
336
+ "grad_norm": 0.5287930468348986,
337
+ "learning_rate": 5e-06,
338
+ "loss": 0.7733,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.0567575161562237,
343
+ "grad_norm": 0.6518686331871915,
344
+ "learning_rate": 5e-06,
345
+ "loss": 0.7633,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.0792357403765103,
350
+ "grad_norm": 0.7380154444162458,
351
+ "learning_rate": 5e-06,
352
+ "loss": 0.7655,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.1017139645967968,
357
+ "grad_norm": 0.5703044113679665,
358
+ "learning_rate": 5e-06,
359
+ "loss": 0.7684,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.1241921888170834,
364
+ "grad_norm": 0.667061719861843,
365
+ "learning_rate": 5e-06,
366
+ "loss": 0.7703,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.14667041303737,
371
+ "grad_norm": 0.49640152865057224,
372
+ "learning_rate": 5e-06,
373
+ "loss": 0.7677,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.1691486372576567,
378
+ "grad_norm": 0.6823293155486599,
379
+ "learning_rate": 5e-06,
380
+ "loss": 0.7733,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1916268614779433,
385
+ "grad_norm": 0.8130260554922801,
386
+ "learning_rate": 5e-06,
387
+ "loss": 0.7694,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.2141050856982298,
392
+ "grad_norm": 0.5402831179025009,
393
+ "learning_rate": 5e-06,
394
+ "loss": 0.7738,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.2365833099185164,
399
+ "grad_norm": 0.7004205303241327,
400
+ "learning_rate": 5e-06,
401
+ "loss": 0.7703,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.259061534138803,
406
+ "grad_norm": 0.5715169691190888,
407
+ "learning_rate": 5e-06,
408
+ "loss": 0.7728,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.2815397583590897,
413
+ "grad_norm": 0.5291552273092583,
414
+ "learning_rate": 5e-06,
415
+ "loss": 0.776,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.3040179825793763,
420
+ "grad_norm": 0.6092348267517466,
421
+ "learning_rate": 5e-06,
422
+ "loss": 0.7745,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.3264962067996628,
427
+ "grad_norm": 0.6042527846865735,
428
+ "learning_rate": 5e-06,
429
+ "loss": 0.7667,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.3489744310199494,
434
+ "grad_norm": 0.5783859809295108,
435
+ "learning_rate": 5e-06,
436
+ "loss": 0.7702,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.371452655240236,
441
+ "grad_norm": 0.7456788631066553,
442
+ "learning_rate": 5e-06,
443
+ "loss": 0.7675,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.3939308794605227,
448
+ "grad_norm": 0.5257587143597946,
449
+ "learning_rate": 5e-06,
450
+ "loss": 0.7688,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.416409103680809,
455
+ "grad_norm": 0.48973885745829204,
456
+ "learning_rate": 5e-06,
457
+ "loss": 0.7712,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.4388873279010959,
462
+ "grad_norm": 0.5351811080578055,
463
+ "learning_rate": 5e-06,
464
+ "loss": 0.7652,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.4613655521213824,
469
+ "grad_norm": 0.5694063448256315,
470
+ "learning_rate": 5e-06,
471
+ "loss": 0.7731,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.483843776341669,
476
+ "grad_norm": 0.6140412877051478,
477
+ "learning_rate": 5e-06,
478
+ "loss": 0.7666,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.5063220005619558,
483
+ "grad_norm": 0.5277178288175658,
484
+ "learning_rate": 5e-06,
485
+ "loss": 0.7654,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.528800224782242,
490
+ "grad_norm": 0.5149765953205256,
491
+ "learning_rate": 5e-06,
492
+ "loss": 0.7681,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.5512784490025289,
497
+ "grad_norm": 0.6475419905061228,
498
+ "learning_rate": 5e-06,
499
+ "loss": 0.7666,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.5737566732228154,
504
+ "grad_norm": 0.5166580562353909,
505
+ "learning_rate": 5e-06,
506
+ "loss": 0.7691,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.596234897443102,
511
+ "grad_norm": 0.4787094497221161,
512
+ "learning_rate": 5e-06,
513
+ "loss": 0.7698,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.6187131216633885,
518
+ "grad_norm": 0.4996359884347099,
519
+ "learning_rate": 5e-06,
520
+ "loss": 0.7678,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.641191345883675,
525
+ "grad_norm": 0.5342877473493819,
526
+ "learning_rate": 5e-06,
527
+ "loss": 0.7676,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.6636695701039619,
532
+ "grad_norm": 0.5893380084853027,
533
+ "learning_rate": 5e-06,
534
+ "loss": 0.7664,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.6861477943242484,
539
+ "grad_norm": 0.5219388717823797,
540
+ "learning_rate": 5e-06,
541
+ "loss": 0.7652,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.708626018544535,
546
+ "grad_norm": 0.48023628858244755,
547
+ "learning_rate": 5e-06,
548
+ "loss": 0.7669,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.7311042427648216,
553
+ "grad_norm": 0.6019840339786192,
554
+ "learning_rate": 5e-06,
555
+ "loss": 0.7639,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.7535824669851081,
560
+ "grad_norm": 0.7082749102315159,
561
+ "learning_rate": 5e-06,
562
+ "loss": 0.7699,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.776060691205395,
567
+ "grad_norm": 0.6095877731067036,
568
+ "learning_rate": 5e-06,
569
+ "loss": 0.7655,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.7985389154256812,
574
+ "grad_norm": 0.5263754173295848,
575
+ "learning_rate": 5e-06,
576
+ "loss": 0.7638,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.821017139645968,
581
+ "grad_norm": 0.5559042865148136,
582
+ "learning_rate": 5e-06,
583
+ "loss": 0.7673,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.8434953638662546,
588
+ "grad_norm": 0.5806755734084227,
589
+ "learning_rate": 5e-06,
590
+ "loss": 0.7637,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.8659735880865411,
595
+ "grad_norm": 0.5027027691217111,
596
+ "learning_rate": 5e-06,
597
+ "loss": 0.7689,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.888451812306828,
602
+ "grad_norm": 0.5835360323428179,
603
+ "learning_rate": 5e-06,
604
+ "loss": 0.7651,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.9109300365271142,
609
+ "grad_norm": 0.5756674505040741,
610
+ "learning_rate": 5e-06,
611
+ "loss": 0.7646,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.933408260747401,
616
+ "grad_norm": 0.6170172971003131,
617
+ "learning_rate": 5e-06,
618
+ "loss": 0.7685,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.9558864849676876,
623
+ "grad_norm": 0.5744859525833788,
624
+ "learning_rate": 5e-06,
625
+ "loss": 0.77,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.9783647091879741,
630
+ "grad_norm": 0.5307996136237888,
631
+ "learning_rate": 5e-06,
632
+ "loss": 0.765,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.998595110986232,
637
+ "eval_loss": 0.8013474345207214,
638
+ "eval_runtime": 476.3278,
639
+ "eval_samples_per_second": 25.168,
640
+ "eval_steps_per_second": 0.395,
641
+ "step": 889
642
+ },
643
+ {
644
+ "epoch": 2.0011239112110144,
645
+ "grad_norm": 0.7180506387912537,
646
+ "learning_rate": 5e-06,
647
+ "loss": 0.7904,
648
+ "step": 890
649
+ },
650
+ {
651
+ "epoch": 2.0236021354313007,
652
+ "grad_norm": 0.8180532035670276,
653
+ "learning_rate": 5e-06,
654
+ "loss": 0.7189,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.0460803596515875,
659
+ "grad_norm": 0.5436885253799979,
660
+ "learning_rate": 5e-06,
661
+ "loss": 0.7202,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.0685585838718743,
666
+ "grad_norm": 0.6619250789509951,
667
+ "learning_rate": 5e-06,
668
+ "loss": 0.7223,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0910368080921606,
673
+ "grad_norm": 0.5679017431009896,
674
+ "learning_rate": 5e-06,
675
+ "loss": 0.7187,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.1135150323124474,
680
+ "grad_norm": 0.580647118753186,
681
+ "learning_rate": 5e-06,
682
+ "loss": 0.7224,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.1359932565327338,
687
+ "grad_norm": 0.5616410388098043,
688
+ "learning_rate": 5e-06,
689
+ "loss": 0.7213,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.1584714807530205,
694
+ "grad_norm": 0.5750449067160542,
695
+ "learning_rate": 5e-06,
696
+ "loss": 0.7233,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.1809497049733073,
701
+ "grad_norm": 0.648340798833132,
702
+ "learning_rate": 5e-06,
703
+ "loss": 0.7234,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.2034279291935936,
708
+ "grad_norm": 0.5562199933691032,
709
+ "learning_rate": 5e-06,
710
+ "loss": 0.7238,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.2259061534138804,
715
+ "grad_norm": 0.5994203497541317,
716
+ "learning_rate": 5e-06,
717
+ "loss": 0.7197,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.2483843776341668,
722
+ "grad_norm": 0.5268766948768074,
723
+ "learning_rate": 5e-06,
724
+ "loss": 0.7239,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.2708626018544535,
729
+ "grad_norm": 0.5268496126487976,
730
+ "learning_rate": 5e-06,
731
+ "loss": 0.7237,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.29334082607474,
736
+ "grad_norm": 0.5327610201359371,
737
+ "learning_rate": 5e-06,
738
+ "loss": 0.7246,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.3158190502950267,
743
+ "grad_norm": 0.5638169818039437,
744
+ "learning_rate": 5e-06,
745
+ "loss": 0.7253,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.3382972745153134,
750
+ "grad_norm": 0.6391691143776261,
751
+ "learning_rate": 5e-06,
752
+ "loss": 0.7257,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.3607754987355998,
757
+ "grad_norm": 0.5627143397713585,
758
+ "learning_rate": 5e-06,
759
+ "loss": 0.7275,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.3832537229558866,
764
+ "grad_norm": 0.6289665122460788,
765
+ "learning_rate": 5e-06,
766
+ "loss": 0.7257,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.405731947176173,
771
+ "grad_norm": 0.5758684477805143,
772
+ "learning_rate": 5e-06,
773
+ "loss": 0.7272,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.4282101713964597,
778
+ "grad_norm": 0.5385204702334082,
779
+ "learning_rate": 5e-06,
780
+ "loss": 0.7264,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.4506883956167465,
785
+ "grad_norm": 0.6150195793596126,
786
+ "learning_rate": 5e-06,
787
+ "loss": 0.7255,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.473166619837033,
792
+ "grad_norm": 0.5418174401143092,
793
+ "learning_rate": 5e-06,
794
+ "loss": 0.7241,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.4956448440573196,
799
+ "grad_norm": 0.5691109067038872,
800
+ "learning_rate": 5e-06,
801
+ "loss": 0.7243,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.518123068277606,
806
+ "grad_norm": 0.5352586504544353,
807
+ "learning_rate": 5e-06,
808
+ "loss": 0.7247,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.5406012924978927,
813
+ "grad_norm": 0.5023069113499318,
814
+ "learning_rate": 5e-06,
815
+ "loss": 0.7214,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.5630795167181795,
820
+ "grad_norm": 0.6122471735672584,
821
+ "learning_rate": 5e-06,
822
+ "loss": 0.7261,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.585557740938466,
827
+ "grad_norm": 0.6574159621177923,
828
+ "learning_rate": 5e-06,
829
+ "loss": 0.7251,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.6080359651587526,
834
+ "grad_norm": 0.5528066749443077,
835
+ "learning_rate": 5e-06,
836
+ "loss": 0.7257,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.630514189379039,
841
+ "grad_norm": 0.631501888391289,
842
+ "learning_rate": 5e-06,
843
+ "loss": 0.7243,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.6529924135993257,
848
+ "grad_norm": 0.6448576692585793,
849
+ "learning_rate": 5e-06,
850
+ "loss": 0.7285,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.675470637819612,
855
+ "grad_norm": 0.6302476804716267,
856
+ "learning_rate": 5e-06,
857
+ "loss": 0.7279,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.697948862039899,
862
+ "grad_norm": 0.6863144289974997,
863
+ "learning_rate": 5e-06,
864
+ "loss": 0.7219,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.7204270862601856,
869
+ "grad_norm": 0.5633795290177185,
870
+ "learning_rate": 5e-06,
871
+ "loss": 0.7241,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.742905310480472,
876
+ "grad_norm": 0.5494311885409552,
877
+ "learning_rate": 5e-06,
878
+ "loss": 0.7282,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.7653835347007587,
883
+ "grad_norm": 0.5030682576319576,
884
+ "learning_rate": 5e-06,
885
+ "loss": 0.7242,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.7878617589210455,
890
+ "grad_norm": 0.5992059557152434,
891
+ "learning_rate": 5e-06,
892
+ "loss": 0.7222,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.810339983141332,
897
+ "grad_norm": 0.5824170874560094,
898
+ "learning_rate": 5e-06,
899
+ "loss": 0.7217,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.832818207361618,
904
+ "grad_norm": 0.5579212327960739,
905
+ "learning_rate": 5e-06,
906
+ "loss": 0.7215,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.855296431581905,
911
+ "grad_norm": 0.5580492783375522,
912
+ "learning_rate": 5e-06,
913
+ "loss": 0.7309,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.8777746558021917,
918
+ "grad_norm": 0.8439296859021013,
919
+ "learning_rate": 5e-06,
920
+ "loss": 0.7266,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.900252880022478,
925
+ "grad_norm": 0.5787147746004252,
926
+ "learning_rate": 5e-06,
927
+ "loss": 0.7282,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.922731104242765,
932
+ "grad_norm": 0.5649986792315236,
933
+ "learning_rate": 5e-06,
934
+ "loss": 0.7279,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.9452093284630516,
939
+ "grad_norm": 0.544211010945195,
940
+ "learning_rate": 5e-06,
941
+ "loss": 0.7227,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.967687552683338,
946
+ "grad_norm": 0.5684918426978717,
947
+ "learning_rate": 5e-06,
948
+ "loss": 0.7311,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.9901657769036247,
953
+ "grad_norm": 0.4877016715810142,
954
+ "learning_rate": 5e-06,
955
+ "loss": 0.723,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.994661421747682,
960
+ "eval_loss": 0.7992855906486511,
961
+ "eval_runtime": 476.027,
962
+ "eval_samples_per_second": 25.183,
963
+ "eval_steps_per_second": 0.395,
964
+ "step": 1332
965
+ },
966
+ {
967
+ "epoch": 2.994661421747682,
968
+ "step": 1332,
969
+ "total_flos": 2230940231270400.0,
970
+ "train_loss": 0.7792791328630648,
971
+ "train_runtime": 78935.918,
972
+ "train_samples_per_second": 8.656,
973
+ "train_steps_per_second": 0.017
974
+ }
975
+ ],
976
+ "logging_steps": 10,
977
+ "max_steps": 1332,
978
+ "num_input_tokens_seen": 0,
979
+ "num_train_epochs": 3,
980
+ "save_steps": 500,
981
+ "stateful_callbacks": {
982
+ "TrainerControl": {
983
+ "args": {
984
+ "should_epoch_stop": false,
985
+ "should_evaluate": false,
986
+ "should_log": false,
987
+ "should_save": true,
988
+ "should_training_stop": true
989
+ },
990
+ "attributes": {}
991
+ }
992
+ },
993
+ "total_flos": 2230940231270400.0,
994
+ "train_batch_size": 8,
995
+ "trial_name": null,
996
+ "trial_params": null
997
+ }
training_eval_loss.png ADDED
training_loss.png ADDED